
#requirements

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.graph_objects as go
import warnings
warnings.filterwarnings('ignore') 
%matplotlib inline
pd.set_option('display.max_columns', 151)


# Loading data #1

#Importing the database with selected columns
df = pd.read_csv('Orginal_database_from_Kaggle/Final database.csv', usecols=['Country', 'Popularity', 'Genre'])
df_1 = pd.read_csv('Orginal_database_from_Kaggle/Final database.csv', usecols=['Country', 'Genre', 'Artist','Title','Album','Cluster','Popularity','Artist_followers'])


# Loading data #2
#Adding extra data set to use in plotly for interpetation country

df_country_iso = pd.read_csv('Country_ISO\countries_codes_and_coordinates.csv') 
df_country_iso = df_country_iso.replace('"','', regex=True) 
df_country_iso = df_country_iso.replace('United Kingdom', 'UK') # adjusting to data in Spotify dataset


# Loading data #3

# Creating dictionary to add 3 letters shortcut to datasetkraj = list(df_country_iso['Country']) #wyciągnięcie krajów z iso
kraj = list(df_country_iso['Country']) #wyciągnięcie krajów z iso
iso = list(df_country_iso['Alpha-3 code']) #wyciągnięcie skrótów krajów z iso
dict = {}
iso = [x.strip(' ') for x in iso] # usnięcie spacji ze skrótów kodów
for i,j in zip(kraj,iso): # tworznie słownika na bazie którego zostanie zapełniona kolumna iso_alpha z df
    dict.setdefault(i,j)


# Loading data #4

df['iso_alpha'] = df['Country'] #dodanie kolmuny iso_alpha z wartościami Country aby dokonać podmiany na trzy literowen zonaczenie

df.replace({"iso_alpha": dict},inplace=True) # podmiana wartosci iso_alpha na ich odpowiednik 3 literowy potrzbne do wykrzystania w plotly do wyświetlania potrzbenych krajów


df['iso_alpha'] = df['Country'] #dodanie kolmuny iso_alpha z wartościami Country aby dokonać podmiany na trzy literowen zonaczenie

df.replace({"iso_alpha": dict},inplace=True) # podmiana wartosci iso_alpha na ich odpowiednik 3 literowy potrzbne do wykrzystania w plotly do wyświetlania pot


df_1.head()


df_1.info(null_counts=False)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 170633 entries, 0 to 170632
Data columns (total 8 columns):
 #   Column            Dtype  
---  ------            -----  
 0   Country           object 
 1   Popularity        float64
 2   Title             object 
 3   Artist            object 
 4   Genre             object 
 5   Artist_followers  object 
 6   Album             object 
 7   Cluster           object 
dtypes: float64(1), object(7)
memory usage: 10.4+ MB


# Data cleansing

df = df.replace('n-a', np.nan)
df = df.dropna()
df_1 = df_1.replace('n-a', np.nan)
df_1 = df_1.dropna()
drop_index_cl = df_1[df_1.Cluster == 'global'].index
drop_index_c = df[df.Country == 'Global'].index
df.drop(drop_index_c,inplace=True)
df_1.drop(drop_index_cl,inplace=True)


Counutries = df_1['Country'].nunique() 
Genres = df_1['Genre'].nunique() 
Titles = df_1['Title'].nunique() 
Albums = df_1['Album'].nunique() 
Artist = df_1['Artist'].nunique()

df_unique = pd.DataFrame({'Countries': [Counutries],'Genres':[Genres], 'Artist': [Artist] , 'Albums':[Albums], 'Title': [Titles],})
df_unique.style.hide_index()


# mean to show on map
by_country = df.groupby('iso_alpha')['Popularity'].mean().reset_index().rename(columns={'iso_alpha': 'Country','Popularity':'Mean Popularity'})


# mean to show on map2

uniq = df_1.groupby(['Country','Cluster'])['Popularity'].count().reset_index().sort_values(by = 'Country')
country = df_1.groupby(['Country','Cluster'])['Popularity'].mean().reset_index().rename(columns={'Popularity':'Mean_Popularity'}).sort_values(by = 'Country')
uniq['Mean_Popularity'] = country['Mean_Popularity']


# mean to show on map3

country_list = by_country
fig = px.choropleth(country_list, locations='Country',
                        color='Mean Popularity', # 
                        hover_name='Country', # column to add to hover information
                        color_continuous_scale=px.colors.sequential.Rainbow,
                        width=600,
                        height=600,
                        projection = 'mercator')
fig.update_layout(title='Map of countries')
fig.show()

uniq = uniq.sort_values(ascending=False, by = 'Popularity')
fig = px.bar(uniq,x=uniq.Country,
            y=uniq.Popularity,
            labels={'Country':'Country', 'Popularity':'The number of occurrences'},    
            color = 'Mean_Popularity',            
            color_continuous_scale = px.colors.sequential.Rainbow)
fig.update_layout(title='Number of songs that were on top list 200 in each country')
fig.update_traces(width=0.4)
fig.show()


fig = px.sunburst(country, 
                  path=['Cluster','Country'], 
                  values='Mean_Popularity',
                  color='Mean_Popularity', 
                  color_continuous_scale=px.colors.sequential.Rainbow,
                  width = 600,
                  height = 800,
                  title= 'Distribution by language'
                 )
fig.show()


country_en = country[country.Cluster == 'english speaking and nordic'].sort_values(ascending=False, by = 'Mean_Popularity')
country_spanish = country[country.Cluster == 'spanish speaking'].sort_values(ascending=False, by = 'Mean_Popularity')
country_portuguese = country[country.Cluster == 'southern europe and portuguese heritage'].sort_values(ascending=False, by = 'Mean_Popularity')

fig = make_subplots(rows=1, cols=3, subplot_titles=( "Spanish speaking", "Southern europe and portuguese heritage", "English speaking and nordic",), shared_yaxes=True, horizontal_spacing=0.1)
fig.add_trace(go.Bar(x=country_en.Country, y=country_en.Mean_Popularity), row=1, col=3)
fig.add_trace(go.Bar(x=country_spanish.Country, y=country_spanish.Mean_Popularity), row=1, col=1)
fig.add_trace(go.Bar(x=country_portuguese.Country, y=country_portuguese.Mean_Popularity), row=1, col=2)
fig.update_layout(height=400, width=1000,
                  title_text="Mean popularity in each country for language cluster", showlegend=False, yaxis_title='Mean popularity', xaxis_title='Country')
fig.update_traces(width=0.4)
fig.show()


count_genre2 = df.groupby('Country')['Genre'].nunique().sort_values(ascending= False)
fig = px.bar(x=count_genre2.index, y=count_genre2.values, labels={'x':'Country', 'y':'The number of different genres'})
fig.update_layout(title='Countries with number of genre diversity ')
fig.update_traces(width=0.4)
fig.show()


genre_counts = df['Genre'].value_counts().nlargest(10)
fig = px.bar(x=genre_counts.index, y=genre_counts, labels={'x':'Genre', 'y':'The number of songs'})
fig.update_layout(title='Top 10 most popular music genres')
fig.update_traces(width=0.4)
fig.show()


result = df.groupby('Country')['Genre'].apply(lambda x: x.value_counts().nlargest(1)).sort_values(ascending=True).reset_index(name='Counts')
result.rename(columns = {'level_1' : 'Legend'}, inplace=True)
wykres2 = px.bar(result, y='Country', x='Counts', color='Legend', orientation='h')
wykres2.update_traces(textposition='inside',width =0.4)
wykres2.update_layout(xaxis_title='Number of occurrences',
                  yaxis_title='Country',
                  height=800)
wykres2.update_layout(title='The most common genre in each country')
wykres2.show()


poland_counts = df.query('Country == "Poland"')['Genre'].value_counts().nlargest(10)
turkey_counts = df.query('Country == "Turkey"')['Genre'].value_counts().nlargest(10)
ecuador_counts = df.query('Country == "Ecuador"')['Genre'].value_counts().nlargest(10)
fig = make_subplots(rows=1, cols=3, subplot_titles=("Poland", "Turkey", "Ecuador"), shared_yaxes=True)
fig.add_trace(go.Bar(x=poland_counts.index, y=poland_counts), row=1, col=1)
fig.add_trace(go.Bar(x=turkey_counts.index, y=turkey_counts), row=1, col=2)
fig.add_trace(go.Bar(x=ecuador_counts.index, y=ecuador_counts), row=1, col=3)
fig.update_layout(height=400, width=1000, title_text="Top 10 most popular music genres in selected country", showlegend=False, yaxis_title='Number of occurrences', xaxis_title='Genre')

                  
fig.show()
fig = px.bar()


#Display the top 10 countries for selected genre
wprowadzony_gatunek = input("Please enter the name of the music genre for which you want to see ordered countries by count: ")
nowy_df = df.loc[df['Genre'] == wprowadzony_gatunek, ['Genre', 'Country','iso_alpha']]
zliczanie = nowy_df['Country'].value_counts()
zliczanie.columns = ['Country', 'Counts']
top_counts = nowy_df[['iso_alpha','Country']].value_counts().reset_index().rename(columns={0 : 'Counts'})
# poloting map from selected countries
country_list = top_counts
fig = px.choropleth(country_list, locations="iso_alpha",
                        color="Counts", # lifeExp is a column of gapminder
                        hover_name="Country", # column to add to hover information
                        color_continuous_scale=px.colors.sequential.Rainbow,
                        width=800,
                        height=800,
                        projection = 'mercator')
fig.show()

# poloting bar from selected countries
fig = px.bar(nowy_df, x=top_counts['Country'], y=top_counts['Counts'], labels={'x':'Country', 'y':'Number of occurrences'})
fig.update_layout(title=f"Count in countries for selected genre ({wprowadzony_gatunek})")
fig.show()

Please enter the name of the music genre for which you want to see ordered countries by count: k-pop

	Country	Popularity	Title	Artist	Genre	Artist_followers	Album	Cluster
0	Global	31833.95	adan y eva	Paulo Londra	argentine hip hop	11427104.0	Adan y Eva	global
1	USA	8.00	adan y eva	Paulo Londra	argentine hip hop	11427104.0	Adan y Eva	english speaking and nordic
2	Argentina	76924.40	adan y eva	Paulo Londra	argentine hip hop	11427104.0	Adan y Eva	spanish speaking
3	Belgium	849.60	adan y eva	Paulo Londra	argentine hip hop	11427104.0	Adan y Eva	english speaking and nordic
4	Switzerland	20739.10	adan y eva	Paulo Londra	argentine hip hop	11427104.0	Adan y Eva	english speaking and nordic

Analysis of genre popularity based on the Kaggle platform's database 'Spotify HUGE database - daily charts over 3 years (2017-2020)¶

Kaggle dataset:¶

Goal of the project:¶

Data exploration and identification of basic issues¶

Table of unique values¶

Data analysis¶

Map of mean popularity¶

Distribution by language¶

Mean popularity in each country for language cluster¶

Countries with number of genre diversity¶

Top 10 most popular music genres¶

The most common genre in each country¶

Top 10 most popular music genres in selected country¶

Number of occurrences in countries for selected genre¶